Single-Cell ADC Scoring for Objective B7-H4 Therapy Response

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for assessing a cancer patient's response to antibody-drug conjugate therapy are prone to variability and subjectivity, necessitating a more repeatable and objective scoring system.

Innovation Solution

A method using a convolutional neural network to analyze immunohistochemically stained tissue samples to compute a Quantitative Continuous Score (QCS) based on single-cell ADC scores, aggregating staining intensities to predict patient response to B7-H4 antibody-drug conjugate therapy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If visual assessment by pathologists is used to score cancer patient response, then the method is simple and quick, but the results are prone to variability and subjectivity

Engineering Contradiction:
Improvescoring accuracyVSAvoidassessment system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces the mechanical/visual assessment system performed by pathologists with an automated image analysis system using convolutional neural networks. This substitution eliminates human subjectivity and variability while maintaining operational simplicity through automated processing of immunohistochemical images.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates a digital copy of the tissue sample through imaging and uses computational algorithms to analyze the copied data rather than direct visual inspection. This allows for precise, repeatable measurement of staining patterns without the limitations of human perception.

Inventive Principle:
Principle #26Copying

2Reliability

If automated image analysis with convolutional neural network is used, then objectivity and repeatability are improved, but the device complexity increases

Engineering Contradiction:
Improvescoring consistencyVSAvoidanalysis system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces complex human visual assessment with an automated computational system that processes images through convolutional neural networks. This substitution achieves high reliability and consistency by eliminating human variability, despite the increased technical complexity of the automated system.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-assessment through automated algorithms that independently analyze the immunohistochemical images without requiring expert pathologist interpretation. The convolutional neural network autonomously identifies and quantifies staining patterns, ensuring consistent results.

Inventive Principle:
Principle #25Self-service

3Measurement precision

If single-cell ADC scores are computed and aggregated, then measurement precision is improved, but the computational complexity and time increase

Engineering Contradiction:
Improveresponse score accuracyVSAvoidscoring computation time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent divides the tissue sample into individual cells and computes ADC scores for each cell separately based on membrane and cytoplasmic staining intensities. This segmentation enables precise measurement at the cellular level, which is then aggregated to produce an overall response score with high accuracy.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent computes detailed staining intensities for multiple cellular compartments (membrane and cytoplasm) and aggregates these partial measurements into a comprehensive response score. This excessive detail in measurement ensures high precision while the automated system manages the computational burden efficiently.

Inventive Principle:
Principle #16Partial or excessive action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Provides a reliable and objective prediction of patient response to B7-H4 antibody-drug conjugate therapy, reducing variability and improving treatment efficacy by identifying patients likely to benefit from the therapy.

Implementation Method 1

Image analysis is performed on the digital image to detect the cancer cells using a convolutional neural network

Methodology Applied
Scientific EffectImage analysis: Image Processing

Implementation Method 2

A tissue sample is immunohistochemically stained using a dye linked to a diagnostic antibody that binds to the protein on the cancer cells

Methodology Applied
Scientific EffectAntibody-antigen binding: Adsorption

Data Source

PatentEP4211663B1A scoring method for an Anti-b7h4 antibody-drug conjugate therapy
Publication Date: 2026.02.18 MEDIMMUNE LTD
  • EP4211663B1 patent drawingFigure 1
  • EP4211663B1 patent drawingFigure 2~3
  • EP4211663B1 patent drawingFigure 4~8

AI summary

The present invention relates to a method for predicting how a cancer patient will respond to an antibody drug conjugate (ADC) therapy involving computing a predictive response score based on single-cell ADC scores for each cancer cell. For each cancer cell, a single-cell ADC score is computed based on the staining intensities of the dye in the membrane and cytoplasm of the cancer cell and in the membranes and cytoplasms of neighboring cancer cells. The present invention also relates to predicting a response of a cancer patient to ADC therapy by aggregating all single-cell ADC scores of the tissue sample using a statistical operation, and the subsequent treatment of cancer with related antibody-drug conjugates.